.png){kind=icon}
返回
Deep learning: a statistical viewpoint
.png){kind=icon}
OA
AI
DOI：10.1017/S0962492921000027.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The remarkable practical success of deep learning has revealed some major surprises from a theoretical perspective. In particular, simple gradient methods easily find near-optimal solutions to non-convex optimization problems, and despite giving a near-perfect fit to training data without any explicit effort to control model complexity, these methods exhibit excellent predictive accuracy. We conjecture that specific principles underlie these phenomena: that overparametrization allows gradient methods to find interpolating solutions, that these methods implicitly impose regularization, and that overparametrization leads to benign overfitting, that is, accurate predictions despite overfitting training data. In this article, we survey recent progress in statistical learning theory that provides examples illustrating these principles in simpler settings. We first review classical uniform convergence results and why they fall short of explaining aspects of the behaviour of deep learning methods. We give examples of implicit regularization in simple settings, where gradient methods lead to minimal norm functions that perfectly fit the training data. Then we review prediction methods that exhibit benign overfitting, focusing on regression problems with quadratic loss. For these methods, we can decompose the prediction rule into a simple component that is useful for prediction and a spiky component that is useful for overfitting but, in a favourable setting, does not harm prediction accuracy. We focus specifically on the linear regime for neural networks, where the network can be approximated by a linear model. In this regime, we demonstrate the success of gradient flow, and we consider benign overfitting with two-layer networks, giving an exact asymptotic analysis that precisely demonstrates the impact of overparametrization. We conclude by highlighting the key challenges that arise in extending these insights to realistic deep learning settings.
Keyword:
TRAINING NEURAL-NETWORKS
VC-DIMENSION
ORACLE INEQUALITIES
SAMPLE COMPLEXITY
LEAST-SQUARES
RISK
BOUNDS
REGRESSION
CLASSIFICATION
ERROR
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
11.3
论文数:
89
被引数:
3.4K
机构
引用论文
Comparison of purified psoralen-inactivated and formalin-inactivated dengue vaccines in mice and nonhuman primates.png)
VaccineOAAI
VaccineIF0
OAAI分享收藏Developing thresholds of potential concern for invasive alien species: Hypotheses and conceptsKoedoeOAAI
KoedoeIF0
OAAI分享收藏
查看更多内容